franzm commited on
Commit
4e97aac
·
1 Parent(s): 0c71f2e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +61 -1
README.md CHANGED
@@ -1,3 +1,63 @@
 
 
 
 
 
 
1
  Query encoder, trained on monolingual (English queries) version of the XOR-TyDi training data, as described in the XOR-TyDi task description https://nlp.cs.washington.edu/xorqa/.
2
 
3
- The model is compatible with the PrimeQA DPR engine, or the Hugging Face DPR engine as shown this example https://huggingface.co/docs/datasets/faiss_es. The model uses the tokenizer from `facebook/dpr-question_encoder-multiset-base`.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-sa-4.0
3
+ ---
4
+
5
+ # Model Description
6
+
7
  Query encoder, trained on monolingual (English queries) version of the XOR-TyDi training data, as described in the XOR-TyDi task description https://nlp.cs.washington.edu/xorqa/.
8
 
9
+ ## Usage
10
+
11
+ The model is compatible with the PrimeQA DPR engine, or the Hugging Face DPR engine as shown this example https://huggingface.co/docs/datasets/faiss_es.
12
+ The model uses the tokenizer from `facebook/dpr-question_encoder-multiset-base`.
13
+
14
+ ## Performance comparison
15
+
16
+ | R@5kt | R@2kt | model |
17
+ |-------|-------|-------|
18
+ | 69.6 | 62.2 | DPR, En, XOR-TyDi paper (https://arxiv.org/pdf/2010.11856.pdf, table 13) |
19
+ | 70.22 | 64.34 | DPR, En, trained on En (human) version of XOR |
20
+
21
+
22
+ ## BibTeX entry and citation info
23
+ ```bibtex
24
+ @inproceedings{asai-etal-2021-xor,
25
+ title = "{XOR} {QA}: Cross-lingual Open-Retrieval Question Answering",
26
+ author = "Asai, Akari and
27
+ Kasai, Jungo and
28
+ Clark, Jonathan and
29
+ Lee, Kenton and
30
+ Choi, Eunsol and
31
+ Hajishirzi, Hannaneh",
32
+ booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
33
+ month = jun,
34
+ year = "2021",
35
+ address = "Online",
36
+ publisher = "Association for Computational Linguistics",
37
+ url = "https://aclanthology.org/2021.naacl-main.46",
38
+ doi = "10.18653/v1/2021.naacl-main.46",
39
+ pages = "547--564",
40
+ }
41
+ ```
42
+
43
+ ```bibtex
44
+ @inproceedings{karpukhin-etal-2020-dense,
45
+ title = "Dense Passage Retrieval for Open-Domain Question Answering",
46
+ author = "Karpukhin, Vladimir and
47
+ Oguz, Barlas and
48
+ Min, Sewon and
49
+ Lewis, Patrick and
50
+ Wu, Ledell and
51
+ Edunov, Sergey and
52
+ Chen, Danqi and
53
+ Yih, Wen-tau",
54
+ booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
55
+ month = nov,
56
+ year = "2020",
57
+ address = "Online",
58
+ publisher = "Association for Computational Linguistics",
59
+ url = "https://aclanthology.org/2020.emnlp-main.550",
60
+ doi = "10.18653/v1/2020.emnlp-main.550",
61
+ pages = "6769--6781",
62
+ }
63
+ ```